corca-ai / LLMFuzzAgent
[Corca / ML] Automatically solved Gandalf AI with LLM
☆48Updated last year
Alternatives and similar repositories for LLMFuzzAgent:
Users that are interested in LLMFuzzAgent are comparing it to the libraries listed below
- Payloads for Attacking Large Language Models☆77Updated 8 months ago
- A benchmark for prompt injection detection systems.☆98Updated last month
- Red-Teaming Language Models with DSPy☆175Updated last month
- Curation of prompts that are known to be adversarial to large language models☆179Updated 2 years ago
- ⚡Simplify and optimize the use of LLMs☆19Updated 10 months ago
- Turning Gandalf against itself. Use LLMs to automate playing Lakera Gandalf challenge without needing to set up an account with a platfor…☆29Updated last year
- A repository of Language Model Vulnerabilities and Exposures (LVEs).☆108Updated last year
- HoneyAgents is a PoC demo of an AI-driven system that combines honeypots with autonomous AI agents to detect and mitigate cyber threats. …☆42Updated last year
- Dropbox LLM Security research code and results☆221Updated 10 months ago
- Risks and targets for assessing LLMs & LLM vulnerabilities☆30Updated 10 months ago
- A guide to LLM hacking: fundamentals, prompt injection, offense, and defense☆145Updated last year
- This project investigates the security of large language models by performing binary classification of a set of input prompts to discover…☆38Updated last year
- A subset of jailbreaks automatically discovered by the Haize Labs haizing suite.☆89Updated 9 months ago
- A toolkit for detecting and protecting against vulnerabilities in Large Language Models (LLMs).☆134Updated last year
- The fastest Trust Layer for AI Agents☆125Updated 3 weeks ago
- Make your GenAI Apps Safe & Secure Test & harden your system prompt☆453Updated 5 months ago
- ☆19Updated last year
- source for llmsec.net☆15Updated 8 months ago
- Codebase of https://arxiv.org/abs/2410.14923☆44Updated 5 months ago
- A text embedding viewer for the Jupyter environment☆19Updated last year
- A library for red-teaming LLM applications with LLMs.☆25Updated 5 months ago
- My inputs for the LLM Gandalf made by Lakera☆41Updated last year
- A prompt injection game to collect data for robust ML research☆54Updated 2 months ago
- PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to a…☆352Updated last year
- Tree of Attacks (TAP) Jailbreaking Implementation☆105Updated last year
- A writeup for the Gandalf prompt injection game.☆37Updated last year
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆115Updated last week
- Every practical and proposed defense against prompt injection.☆412Updated last month
- Masked Python SDK wrapper for OpenAI API. Use public LLM APIs securely.☆116Updated 2 years ago
- ☆31Updated 4 months ago